Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code and mathematical notations

    oai_token-act-pair · gemini-2.0-flash

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.84
     myſelf
    -0.79
     saites
    -0.75
    Portail
    -0.73
    InjectAttribute
    -0.71
    الحياه
    -0.70
    ніципалі
    -0.68
    RenderAtEndOf
    -0.68
    felves
    -0.68
    neſs
    -0.68
    POSITIVE LOGITS
     OFDb
    0.47
    唑
    0.46
    omyces
    0.45
    fta
    0.45
     here
    0.45
    mi
    0.43
     review
    0.43
     f
    0.43
     at
    0.43
     plane
    0.42
    Act Density 1.153%

    No Known Activations